© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 150913
    Prev
    Next
    INDEX
    Explanations

    latest installment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_18_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     худож
    0.33
     aren
    0.33
     Wahl
    0.33
     ć
    0.32
    hrad
    0.32
     Çocuk
    0.32
    łuż
    0.31
    ïque
    0.31
     retreating
    0.31
     машин
    0.31
    POSITIVE LOGITS
     debates
    0.38
    ﻢ
    0.38
     negoti
    0.37
    الم
    0.35
    לי
    0.34
     irony
    0.34
    ან
    0.33
     lastName
    0.33
    لمين
    0.33
    k
    0.33
    Activations Density 0.000%

    No Known Activations